From: David Hildenbrand <david@redhat.com>
To: qemu-devel@nongnu.org
Cc: Thomas Huth <thuth@redhat.com>,
David Hildenbrand <david@redhat.com>,
Cornelia Huck <cohuck@redhat.com>,
Richard Henderson <richard.henderson@linaro.org>,
Laurent Vivier <laurent@vivier.eu>,
Halil Pasic <pasic@linux.ibm.com>,
Christian Borntraeger <borntraeger@de.ibm.com>,
qemu-s390x@nongnu.org
Subject: [PATCH v4 07/26] s390x/tcg: Simplify vfma64() handling
Date: Tue, 8 Jun 2021 11:23:18 +0200 [thread overview]
Message-ID: <20210608092337.12221-8-david@redhat.com> (raw)
In-Reply-To: <20210608092337.12221-1-david@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
target/s390x/helper.h | 2 --
target/s390x/translate_vx.c.inc | 8 +++----
target/s390x/vec_fpu_helper.c | 42 +++++++++++++--------------------
3 files changed, 20 insertions(+), 32 deletions(-)
diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index e832680236..3c87593553 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -267,9 +267,7 @@ DEF_HELPER_FLAGS_4(gvec_vflr64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vflr64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
DEF_HELPER_FLAGS_6(gvec_vfma64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_6(gvec_vfma64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
DEF_HELPER_FLAGS_6(gvec_vfms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
-DEF_HELPER_FLAGS_6(gvec_vfms64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32)
DEF_HELPER_FLAGS_4(gvec_vfsq64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32)
DEF_HELPER_FLAGS_5(gvec_vfs64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32)
DEF_HELPER_4(gvec_vftci64, void, ptr, cptr, env, i32)
diff --git a/target/s390x/translate_vx.c.inc b/target/s390x/translate_vx.c.inc
index 1404471881..4b5bf0a7e3 100644
--- a/target/s390x/translate_vx.c.inc
+++ b/target/s390x/translate_vx.c.inc
@@ -2589,7 +2589,6 @@ static DisasJumpType op_vfma(DisasContext *s, DisasOps *o)
{
const uint8_t m5 = get_field(s, m5);
const uint8_t fpf = get_field(s, m6);
- const bool se = extract32(m5, 3, 1);
gen_helper_gvec_4_ptr *fn;
if (fpf != FPF_LONG || extract32(m5, 0, 3)) {
@@ -2598,13 +2597,12 @@ static DisasJumpType op_vfma(DisasContext *s, DisasOps *o)
}
if (s->fields.op2 == 0x8f) {
- fn = se ? gen_helper_gvec_vfma64s : gen_helper_gvec_vfma64;
+ fn = gen_helper_gvec_vfma64;
} else {
- fn = se ? gen_helper_gvec_vfms64s : gen_helper_gvec_vfms64;
+ fn = gen_helper_gvec_vfms64;
}
gen_gvec_4_ptr(get_field(s, v1), get_field(s, v2),
- get_field(s, v3), get_field(s, v4), cpu_env,
- 0, fn);
+ get_field(s, v3), get_field(s, v4), cpu_env, m5, fn);
return DISAS_NEXT;
}
diff --git a/target/s390x/vec_fpu_helper.c b/target/s390x/vec_fpu_helper.c
index 2ced6fcfaf..23b38df158 100644
--- a/target/s390x/vec_fpu_helper.c
+++ b/target/s390x/vec_fpu_helper.c
@@ -374,12 +374,12 @@ static void vfma64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
int i;
for (i = 0; i < 2; i++) {
- const uint64_t a = s390_vec_read_element64(v2, i);
- const uint64_t b = s390_vec_read_element64(v3, i);
- const uint64_t c = s390_vec_read_element64(v4, i);
- uint64_t ret = float64_muladd(a, b, c, flags, &env->fpu_status);
+ const float64 a = s390_vec_read_float64(v2, i);
+ const float64 b = s390_vec_read_float64(v3, i);
+ const float64 c = s390_vec_read_float64(v4, i);
+ const float64 ret = float64_muladd(a, b, c, flags, &env->fpu_status);
- s390_vec_write_element64(&tmp, i, ret);
+ s390_vec_write_float64(&tmp, i, ret);
vxc = check_ieee_exc(env, i, false, &vec_exc);
if (s || vxc) {
break;
@@ -389,29 +389,21 @@ static void vfma64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3,
*v1 = tmp;
}
-void HELPER(gvec_vfma64)(void *v1, const void *v2, const void *v3,
- const void *v4, CPUS390XState *env, uint32_t desc)
-{
- vfma64(v1, v2, v3, v4, env, false, 0, GETPC());
-}
-
-void HELPER(gvec_vfma64s)(void *v1, const void *v2, const void *v3,
- const void *v4, CPUS390XState *env, uint32_t desc)
-{
- vfma64(v1, v2, v3, v4, env, true, 0, GETPC());
+#define DEF_GVEC_VFMA_B(NAME, FLAGS, BITS) \
+void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2, const void *v3, \
+ const void *v4, CPUS390XState *env, \
+ uint32_t desc) \
+{ \
+ const bool se = extract32(simd_data(desc), 3, 1); \
+ \
+ vfma##BITS(v1, v2, v3, v4, env, se, FLAGS, GETPC()); \
}
-void HELPER(gvec_vfms64)(void *v1, const void *v2, const void *v3,
- const void *v4, CPUS390XState *env, uint32_t desc)
-{
- vfma64(v1, v2, v3, v4, env, false, float_muladd_negate_c, GETPC());
-}
+#define DEF_GVEC_VFMA(NAME, FLAGS) \
+ DEF_GVEC_VFMA_B(NAME, FLAGS, 64)
-void HELPER(gvec_vfms64s)(void *v1, const void *v2, const void *v3,
- const void *v4, CPUS390XState *env, uint32_t desc)
-{
- vfma64(v1, v2, v3, v4, env, true, float_muladd_negate_c, GETPC());
-}
+DEF_GVEC_VFMA(vfma, 0)
+DEF_GVEC_VFMA(vfms, float_muladd_negate_c)
void HELPER(gvec_vftci64)(void *v1, const void *v2, CPUS390XState *env,
uint32_t desc)
--
2.31.1
next prev parent reply other threads:[~2021-06-08 9:30 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-08 9:23 [PATCH v4 00/26] s390x/tcg: Implement Vector enhancements facility and switch to z14 David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 01/26] s390x/tcg: Fix FP CONVERT TO (LOGICAL) FIXED NaN handling David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 02/26] s390x/tcg: Fix instruction name for VECTOR FP LOAD (LENGTHENED|ROUNDED) David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 03/26] s390x/tcg: Simplify vop64_3() handling David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 04/26] s390x/tcg: Simplify vop64_2() handling David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 05/26] s390x/tcg: Simplify vfc64() handling David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 06/26] s390x/tcg: Simplify vftci64() handling David Hildenbrand
2021-06-08 9:23 ` David Hildenbrand [this message]
2021-06-08 9:23 ` [PATCH v4 08/26] s390x/tcg: Simplify vfll32() handling David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 09/26] s390x/tcg: Simplify vflr64() handling David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 10/26] s390x/tcg: Simplify wfc64() handling David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 11/26] s390x/tcg: Implement VECTOR BIT PERMUTE David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 12/26] s390x/tcg: Implement VECTOR MULTIPLY SUM LOGICAL David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 13/26] s390x/tcg: Implement 32/128 bit for VECTOR FP (ADD|DIVIDE|MULTIPLY|SUBTRACT) David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 14/26] s390x/tcg: Implement 32/128 bit for VECTOR (LOAD FP INTEGER|FP SQUARE ROOT) David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 15/26] s390x/tcg: Implement 32/128 bit for VECTOR FP COMPARE * David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 16/26] s390x/tcg: Implement 32/128 bit for VECTOR FP COMPARE (AND SIGNAL) SCALAR David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 17/26] s390x/tcg: Implement 64 bit for VECTOR FP LOAD LENGTHENED David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 18/26] s390x/tcg: Implement 128 bit for VECTOR FP LOAD ROUNDED David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 19/26] s390x/tcg: Implement 32/128 bit for VECTOR FP PERFORM SIGN OPERATION David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 20/26] s390x/tcg: Implement 32/128 bit for VECTOR FP TEST DATA CLASS IMMEDIATE David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 21/26] s390x/tcg: Implement 32/128 bit for VECTOR FP MULTIPLY AND (ADD|SUBTRACT) David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 22/26] s390x/tcg: Implement VECTOR FP NEGATIVE " David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 23/26] s390x/tcg: Implement VECTOR FP (MAXIMUM|MINIMUM) David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 24/26] linux-user: elf: s390x: Prepare for Vector enhancements facility David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 25/26] s390x/tcg: We support " David Hildenbrand
2021-06-08 9:23 ` [PATCH v4 26/26] s390x/cpumodel: Bump up QEMU model to a stripped-down IBM z14 GA2 David Hildenbrand
2021-06-09 9:09 ` [PATCH v4 00/26] s390x/tcg: Implement Vector enhancements facility and switch to z14 Cornelia Huck
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210608092337.12221-8-david@redhat.com \
--to=david@redhat.com \
--cc=borntraeger@de.ibm.com \
--cc=cohuck@redhat.com \
--cc=laurent@vivier.eu \
--cc=pasic@linux.ibm.com \
--cc=qemu-devel@nongnu.org \
--cc=qemu-s390x@nongnu.org \
--cc=richard.henderson@linaro.org \
--cc=thuth@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).